Kai Jia

Zheng Li, Qingxiu Dong, Jingyuan Ma et al. · pku

Recently, large reasoning models demonstrate exceptional performance on various tasks. However, reasoning models always consume excessive tokens even for simple queries, leading to resource waste and prolonged user latency. To address this challenge, we propose SelfBudgeter - a self-adaptive reasoning strategy for efficient and controllable reasoning. Specifically, we first train the model to self-estimate the required reasoning budget based on the query. We then introduce budget-guided GRPO for reinforcement learning, which effectively maintains accuracy while reducing output length. Experimental results demonstrate that SelfBudgeter dynamically allocates budgets according to problem complexity, achieving an average response length compression of 61% on math reasoning tasks while maintaining accuracy. Furthermore, SelfBudgeter allows users to see how long generation will take and decide whether to continue or stop. Additionally, users can directly control the reasoning length by setting token budgets upfront.

Kai Jia, Hongwen Zhang, Liang An et al.

Regression-based methods have shown high efficiency and effectiveness for multi-view human mesh recovery. The key components of a typical regressor lie in the feature extraction of input views and the fusion of multi-view features. In this paper, we present Pixel-aligned Feedback Fusion (PaFF) for accurate yet efficient human mesh recovery from multi-view images. PaFF is an iterative regression framework that performs feature extraction and fusion alternately. At each iteration, PaFF extracts pixel-aligned feedback features from each input view according to the reprojection of the current estimation and fuses them together with respect to each vertex of the downsampled mesh. In this way, our regressor can not only perceive the misalignment status of each view from the feedback features but also correct the mesh parameters more effectively based on the feature fusion on mesh vertices. Additionally, our regressor disentangles the global orientation and translation of the body mesh from the estimation of mesh parameters such that the camera parameters of input views can be better utilized in the regression process. The efficacy of our method is validated in the Human3.6M dataset via comprehensive ablation experiments, where PaFF achieves 33.02 MPJPE and brings significant improvements over the previous best solutions by more than 29%. The project page with code and video results can be found at https://kairobo.github.io/PaFF/.

Kai Jia, Martin Rinard

$L_0$ regularization of neural networks is a fundamental problem. In addition to regularizing models for better generalizability, $L_0$ regularization also applies to selecting input features and training sparse neural networks. There is a large body of research on related topics, some with quite complicated methods. In this paper, we show that a straightforward formulation, BinMask, which multiplies weights with deterministic binary masks and uses the identity straight-through estimator for backpropagation, is an effective $L_0$ regularizer. We evaluate BinMask on three tasks: feature selection, network sparsification, and model regularization. Despite its simplicity, BinMask achieves competitive performance on all the benchmarks without task-specific tuning compared to methods designed for each task. Our results suggest that decoupling weights from mask optimization, which has been widely adopted by previous work, is a key component for effective $L_0$ regularization.

Guoxin Chen, Jie Chen, Lei Chen et al.

Autonomous AI research has advanced rapidly, but long-horizon ML research engineering remains difficult: agents must sustain coherent progress across task comprehension, environment setup, implementation, experimentation, and debugging over hours or days. We introduce AiScientist, a system for autonomous long-horizon engineering for ML research built on a simple principle: strong long-horizon performance requires both structured orchestration and durable state continuity. To this end, AiScientist combines hierarchical orchestration with a permission-scoped File-as-Bus workspace: a top-level Orchestrator maintains stage-level control through concise summaries and a workspace map, while specialized agents repeatedly re-ground on durable artifacts such as analyses, plans, code, and experimental evidence rather than relying primarily on conversational handoffs, yielding thin control over thick state. Across two complementary benchmarks, AiScientist improves PaperBench score by 10.54 points on average over the best matched baseline and achieves 81.82 Any Medal% on MLE-Bench Lite. Ablation studies further show that File-as-Bus protocol is a key driver of performance, reducing PaperBench by 6.41 points and MLE-Bench Lite by 31.82 points when removed. These results suggest that long-horizon ML research engineering is a systems problem of coordinating specialized work over durable project state, rather than a purely local reasoning problem.

Zirun Guo, Minjie Hong, Feng Zhang et al.

Multimodal large language models (MLLMs) that think with images can interactively use tools to reason about visual inputs, but current approaches often rely on a narrow set of tools with limited real-world necessity and scalability. In this work, we first reveal a critical and previously overlooked weakness: even state-of-the-art MLLMs are surprisingly brittle, showing significant performance degradation on images with simple orientation changes or natural corruptions, underscoring the need for more robust tool-based reasoning. To address this, we propose CodeVision, a flexible and scalable code-as-tool framework where the model generates code as a universal interface to invoke any image operation, moving beyond fixed tool registries. We train our model using a two-stage methodology, beginning with Supervised Fine-Tuning (SFT) on a high-quality dataset curated for complex, multi-turn tool composition and error recovery, followed by Reinforcement Learning (RL) with a novel and dense process reward function to encourage strategic and efficient tool use. To facilitate this research, we construct new SFT and RL datasets and introduce a challenging new benchmark suite designed to rigorously evaluate robustness to orientation changes and multi-tool reasoning. Experiments on Qwen2.5-VL and Qwen3-VL series show that our approach significantly improves model performance and fosters emergent capabilities such as flexible tool composition, efficient chained execution, and robust error recovery from runtime feedback. Code is available at https://github.com/ByteDance-BandAI/CodeVision.

Jiale Zhao, Guoxin Chen, Fanzhe Meng et al.

Achieving mastery in real world software engineering tasks is fundamentally bottlenecked by the scarcity of large scale, high quality training data. Scaling such data has been limited by the complexity of environment setup, unit test generation, and problem statement curation. In this paper, we propose ScaleSWE, an automated, sandboxed multi agent workflow designed to construct high quality SWE data at scale. The system coordinates three specialized agents for environment setup, test creation, and problem description synthesis to process 6 million pull requests across 5200 repositories, producing Scale SWE Data: 100k verified SWE instances, the largest such dataset to date. It substantially surpasses existing real world datasets in repository diversity and reflects realistic task complexity. We further demonstrate the dataset utility for training by distilling 71498 high quality trajectories and finetuning Qwen30BA3BInstruct to produce ScaleSWE Agent. Our agent achieves a 64 resolve rate on SWE Bench Verified a nearly three fold improvement over the base model. ScaleSWE provides a scalable, reproducible approach for data construction to advance LLM based software engineering. Scale SWE will be publicly available.

Guoxin Chen, Fanzhe Meng, Jiale Zhao et al.

Current benchmarks for code agents primarily assess narrow, repository-specific fixes, overlooking critical real-world challenges such as cross-repository reasoning, domain-specialized problem solving, dependency-driven migration, and full-repository generation. To address this gap, we introduce BeyondSWE, a comprehensive benchmark that broadens existing evaluations along two axes - resolution scope and knowledge scope - using 500 real-world instances across four distinct settings. Experimental results reveal a significant capability gap: even frontier models plateau below 45% success, and no single model performs consistently across task types. To systematically investigate the role of external knowledge, we develop SearchSWE, a framework that integrates deep search with coding abilities. Our experiments show that search augmentation yields inconsistent gains and can in some cases degrade performance, highlighting the difficulty of emulating developer-like workflows that interleave search and reasoning during coding tasks. This work offers both a realistic, challenging evaluation benchmark and a flexible framework to advance research toward more capable code agents.

Minghao Li, Ying Zeng, Zhihao Cheng et al.

The advent of Deep Research agents has substantially reduced the time required for conducting extensive research tasks. However, these tasks inherently demand rigorous standards of factual accuracy and comprehensiveness, necessitating thorough evaluation before widespread adoption. In this paper, we propose ReportBench, a systematic benchmark designed to evaluate the content quality of research reports generated by large language models (LLMs). Our evaluation focuses on two critical dimensions: (1) the quality and relevance of cited literature, and (2) the faithfulness and veracity of the statements within the generated reports. ReportBench leverages high-quality published survey papers available on arXiv as gold-standard references, from which we apply reverse prompt engineering to derive domain-specific prompts and establish a comprehensive evaluation corpus. Furthermore, we develop an agent-based automated framework within ReportBench that systematically analyzes generated reports by extracting citations and statements, checking the faithfulness of cited content against original sources, and validating non-cited claims using web-based resources. Empirical evaluations demonstrate that commercial Deep Research agents such as those developed by OpenAI and Google consistently generate more comprehensive and reliable reports than standalone LLMs augmented with search or browsing tools. However, there remains substantial room for improvement in terms of the breadth and depth of research coverage, as well as factual consistency. The complete code and data will be released at the following link: https://github.com/ByteDance-BandAI/ReportBench

Kai Jia, Pasapol Saowakon, Limor Appelbaum et al.

We take a formal approach to the explainability problem of machine learning systems. We argue against the practice of interpreting black-box models via attributing scores to input components due to inherently conflicting goals of attribution-based interpretation. We prove that no attribution algorithm satisfies specificity, additivity, completeness, and baseline invariance. We then formalize the concept, sound explanation, that has been informally adopted in prior work. A sound explanation entails providing sufficient information to causally explain the predictions made by a system. Finally, we present the application of feature selection as a sound explanation for cancer prediction models to cultivate trust among clinicians.

Zirun Guo, Feng Zhang, Kai Jia et al.

We propose LLM-Interleaved (LLM-I), a flexible and dynamic framework that reframes interleaved image-text generation as a tool-use problem. LLM-I is designed to overcome the "one-tool" bottleneck of current unified models, which are limited to synthetic imagery and struggle with tasks requiring factual grounding or programmatic precision. Our framework empowers a central LLM or MLLM agent to intelligently orchestrate a diverse toolkit of specialized visual tools, including online image search, diffusion-based generation, code execution, and image editing. The agent is trained to select and apply these tools proficiently via a Reinforcement Learning (RL) framework that features a hybrid reward system combining rule-based logic with judgments from LLM and MLLM evaluators. Trained on a diverse new dataset using four different model backbones, LLM-I demonstrates state-of-the-art performance, outperforming existing methods by a large margin across four benchmarks. We also introduce a novel test-time scaling strategy that provides further performance gains. Project Page: https://github.com/ByteDance-BandAI/LLM-I.

Huaixiao Tou, Ying Zeng, Yuemeng Li et al.

We present ShoppingComp, a challenging real-world benchmark for comprehensively evaluating LLM-powered shopping agents on three core capabilities: precise product retrieval, expert-level report generation, and safety critical decision making. Unlike prior e-commerce benchmarks, ShoppingComp introduces difficult product discovery queries with many constraints, while guaranteeing open-world products and enabling easy verification of agent outputs. The benchmark comprises 145 instances and 558 scenarios, curated by 35 experts to reflect authentic shopping needs. Results reveal stark limitations of current LLMs: even state-of-the-art models achieve low performance (e.g., 17.76\% for GPT-5.2, 15.82\% for Gemini-3-Pro).Error analysis reflects limitations in core agent competencies, including information grounding in open-world environments, reliable verification of multi-constraint requirements, consistent reasoning over noisy and conflicting evidence, and risk-aware decision making. By exposing these capability gaps, ShoppingComp characterizes the trust threshold that AI systems must cross before they can be proactively trusted for reliable real-world decision making. Our code and dataset are available at https://github.com/ByteDance-BandAI/ShoppingComp.

Shiye Lei, Zhihao Cheng, Kai Jia et al.

Large language models (LLMs) have recently demonstrated remarkable progress in reasoning capabilities through reinforcement learning with verifiable rewards (RLVR). By leveraging simple rule-based rewards, RL effectively incentivizes LLMs to produce extended chain-of-thought (CoT) reasoning trajectories, progressively guiding them toward correct answers. However, existing approaches remain largely heuristic and intuition-driven, limiting the development of principled methodologies. In this paper, we present a theoretical characterization of LLM reasoning grounded in information bottleneck (IB) principle, introducing IB-aware reasoning optimization (IBRO), a framework that encourages reasoning trajectories to be both informative about the final correct answer and generalizable across diverse prompts. We derive a practical token-level surrogate objective and propose an efficient approximation, resulting in the lightweight IB regularization method. This technique integrates seamlessly into existing RL-based post-training frameworks without additional computational overhead, requiring only a one-line code modification. Empirically, we validate IB regularization across multiple mathematical reasoning benchmarks and RL algorithms, demonstrating consistent improvements in LLM reasoning performance.

Yichen Han, Xiaoyang Hao, Keming Chen et al.

Text-to-speech (TTS) synthesis has seen renewed progress under the discrete modeling paradigm. Existing autoregressive approaches often rely on single-codebook representations, which suffer from significant information loss. Even with post-hoc refinement techniques such as flow matching, these methods fail to recover fine-grained details (e.g., prosodic nuances, speaker-specific timbres), especially in challenging scenarios like singing voice or music synthesis. We propose QTTS, a novel TTS framework built upon our new audio codec, QDAC. The core innovation of QDAC lies in its end-to-end training of an ASR-based auto-regressive network with a GAN, which achieves superior semantic feature disentanglement for scalable, near-lossless compression. QTTS models these discrete codes using two innovative strategies: the Hierarchical Parallel architecture, which uses a dual-AR structure to model inter-codebook dependencies for higher-quality synthesis, and the Delay Multihead approach, which employs parallelized prediction with a fixed delay to accelerate inference speed. Our experiments demonstrate that the proposed framework achieves higher synthesis quality and better preserves expressive content compared to baseline. This suggests that scaling up compression via multi-codebook modeling is a promising direction for high-fidelity, general-purpose speech and audio generation.

Siyao Song, Cong Ma, Zhihao Cheng et al.

Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcome-based supervision to strengthen internal LLM reasoning, often leading to inefficient exploration and sparse rewards. To mitigate this issue, we propose Expert-Assisted Policy Optimization (EAPO), a novel RL framework that enhances exploration by incorporating multi-turn interactions with external experts during training. Unlike prior methods, where policies reason in isolation, EAPO incentivizes the policy to adaptively determine when and how to consult experts, yielding richer reward signals and more reliable reasoning trajectories. External assistance ultimately internalizes expert knowledge into the policy model, amplifying the model's inherent reasoning capabilities. During evaluation, the policy model has been well-optimized to solve questions independently, producing improved reasoning paths and more accurate solutions. Experiments on mathematical reasoning benchmarks, including AIME 2024, AIME 2025, and AIMO 2025, show that EAPO consistently outperforms expert-assisted workflow, expert-distilled models, and RL baselines, with an average gain of 5 points over self-exploratory models.

Kai Jia, Martin Rinard

Deep neural networks are an attractive tool for compressing the control policy lookup tables in systems such as the Airborne Collision Avoidance System (ACAS). It is vital to ensure the safety of such neural controllers via verification techniques. The problem of analyzing ACAS Xu networks has motivated many successful neural network verifiers. These verifiers typically analyze the internal computation of neural networks to decide whether a property regarding the input/output holds. The intrinsic complexity of neural network computation renders such verifiers slow to run and vulnerable to floating-point error. This paper revisits the original problem of verifying ACAS Xu networks. The networks take low-dimensional sensory inputs with training data provided by a precomputed lookup table. We propose to prepend an input quantization layer to the network. Quantization allows efficient verification via input state enumeration, whose complexity is bounded by the size of the quantization space. Quantization is equivalent to nearest-neighbor interpolation at run time, which has been shown to provide acceptable accuracy for ACAS in simulation. Moreover, our technique can deliver exact verification results immune to floating-point error if we directly enumerate the network outputs on the target inference implementation or on an accurate simulation of the target implementation.

Weihao Gao, Xiangjun Fan, Chong Wang et al.

One of the core problems in large-scale recommendations is to retrieve top relevant candidates accurately and efficiently, preferably in sub-linear time. Previous approaches are mostly based on a two-step procedure: first learn an inner-product model, and then use some approximate nearest neighbor (ANN) search algorithm to find top candidates. In this paper, we present Deep Retrieval (DR), to learn a retrievable structure directly with user-item interaction data (e.g. clicks) without resorting to the Euclidean space assumption in ANN algorithms. DR's structure encodes all candidate items into a discrete latent space. Those latent codes for the candidates are model parameters and learnt together with other neural network parameters to maximize the same objective function. With the model learnt, a beam search over the structure is performed to retrieve the top candidates for reranking. Empirically, we first demonstrate that DR, with sub-linear computational complexity, can achieve almost the same accuracy as the brute-force baseline on two public datasets. Moreover, we show that, in a live production recommendation system, a deployed DR approach significantly outperforms a well-tuned ANN baseline in terms of engagement metrics. To the best of our knowledge, DR is among the first non-ANN algorithms successfully deployed at the scale of hundreds of millions of items for industrial recommendation systems.

Kai Jia, Martin Rinard

Concerned with the reliability of neural networks, researchers have developed verification techniques to prove their robustness. Most verifiers work with real-valued networks. Unfortunately, the exact (complete and sound) verifiers face scalability challenges and provide no correctness guarantees due to floating point errors. We argue that Binarized Neural Networks (BNNs) provide comparable robustness and allow exact and significantly more efficient verification. We present a new system, EEV, for efficient and exact verification of BNNs. EEV consists of two parts: (i) a novel SAT solver that speeds up BNN verification by natively handling the reified cardinality constraints arising in BNN encodings; and (ii) strategies to train solver-friendly robust BNNs by inducing balanced layer-wise sparsity and low cardinality bounds, and adaptively cancelling the gradients. We demonstrate the effectiveness of EEV by presenting the first exact verification results for L-inf-bounded adversarial robustness of nontrivial convolutional BNNs on the MNIST and CIFAR10 datasets. Compared to exact verification of real-valued networks of the same architectures on the same tasks, EEV verifies BNNs hundreds to thousands of times faster, while delivering comparable verifiable accuracy in most cases.

Kai Jia, Martin Rinard

Researchers have developed neural network verification algorithms motivated by the need to characterize the robustness of deep neural networks. The verifiers aspire to answer whether a neural network guarantees certain properties with respect to all inputs in a space. However, many verifiers inaccurately model floating point arithmetic but do not thoroughly discuss the consequences. We show that the negligence of floating point error leads to unsound verification that can be systematically exploited in practice. For a pretrained neural network, we present a method that efficiently searches inputs as witnesses for the incorrectness of robustness claims made by a complete verifier. We also present a method to construct neural network architectures and weights that induce wrong results of an incomplete verifier. Our results highlight that, to achieve practically reliable verification of neural networks, any verification system must accurately (or conservatively) model the effects of any floating point computations in the network inference or verification system.

Chao Peng, Tete Xiao, Zeming Li et al.

The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network, new framework, or novel loss design. But mini-batch size, a key factor in the training, has not been well studied. In this paper, we propose a Large MiniBatch Object Detector (MegDet) to enable the training with much larger mini-batch size than before (e.g. from 16 to 256), so that we can effectively utilize multiple GPUs (up to 128 in our experiments) to significantly shorten the training time. Technically, we suggest a learning rate policy and Cross-GPU Batch Normalization, which together allow us to successfully train a large mini-batch detector in much less time (e.g., from 33 hours to 4 hours), and achieve even better accuracy. The MegDet is the backbone of our submission (mmAP 52.5%) to COCO 2017 Challenge, where we won the 1st place of Detection task.

The Theano Development Team, Rami Al-Rfou, Guillaume Alain et al.

Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements. Theano is being actively and continuously developed since 2008, multiple frameworks have been built on top of it and it has been used to produce many state-of-the-art machine learning models. The present article is structured as follows. Section I provides an overview of the Theano software and its community. Section II presents the principal features of Theano and how to use them, and compares them with other similar projects. Section III focuses on recently-introduced functionalities and improvements. Section IV compares the performance of Theano against Torch7 and TensorFlow on several machine learning models. Section V discusses current limitations of Theano and potential ways of improving it.